© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85513
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -1.81
     its
    -1.63
    \
    -1.61
    _
    -1.55
     by
    -1.50
     ‘
    -1.50
     about
    -1.49
    -
    -1.44
    으면
    -1.41
     then
    -1.38
    POSITIVE LOGITS
     anderen
    1.78
     écout
    1.62
     farby
    1.55
     venons
    1.55
    僦
    1.47
     testé
    1.46
     devons
    1.46
     andern
    1.45
     Según
    1.42
     tkan
    1.42
    Activations Density 0.001%

    No Known Activations